{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/towards-summarizing-multiple-documents-with","title":"Summarizing Multiple Documents with Conversational Structure for Meta-Review Generation","arxiv_id":"2305.01498","date":"2023-05-02","proceeding":null,"authors":["Miao Li","Eduard Hovy","Jey Han Lau"],"abstract":"We present PeerSum, a novel dataset for generating meta-reviews of scientific papers. The meta-reviews can be interpreted as abstractive summaries of reviews, multi-turn discussions and the paper abstract. These source documents have rich inter-document relationships with an explicit hierarchical conversational structure, cross-references and (occasionally) conflicting information. To introduce the structural inductive bias into pre-trained language models, we introduce Rammer ( Relationship-aware Multi-task Meta-review Generator), a model that uses sparse attention based on the conversational structure and a multi-task training objective that predicts metadata features (e.g., review ratings). Our experimental results show that Rammer outperforms other strong baseline models in terms of a suite of automatic evaluation metrics. Further analyses, however, reveal that RAMMER and other models struggle to handle conflicts in source documents of PeerSum, suggesting meta-review generation is a challenging task and a promising avenue for further research.","url_abs":"https://arxiv.org/abs/2305.01498v4","url_pdf":"https://arxiv.org/pdf/2305.01498v4.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"towards-summarizing-multiple-documents-with","repo_url":"https://github.com/oaimli/peersum","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"document-summarization","task_name":"Document Summarization"},{"task_slug":"inductive-bias","task_name":"Inductive Bias"},{"task_slug":"multi-document-summarization","task_name":"Multi-Document Summarization"},{"task_slug":"review-generation","task_name":"Review Generation"},{"task_slug":"text-generation","task_name":"Text Generation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2305.01498","atlas_url":"https://app.syntology.ai/?focus=2305.01498","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}